CN115097826A - Vehicle turning track planning method and device - Google Patents
Vehicle turning track planning method and device Download PDFInfo
- Publication number
- CN115097826A CN115097826A CN202210694631.2A CN202210694631A CN115097826A CN 115097826 A CN115097826 A CN 115097826A CN 202210694631 A CN202210694631 A CN 202210694631A CN 115097826 A CN115097826 A CN 115097826A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- track
- turning
- segmented
- trajectory
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000011218 segmentation Effects 0.000 claims abstract description 66
- 230000006870 function Effects 0.000 claims description 30
- 238000004422 calculation algorithm Methods 0.000 claims description 25
- 238000003860 storage Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 13
- 230000002093 peripheral effect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 230000008901 benefit Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
Abstract
The invention discloses a vehicle turning track planning method and device, relates to the field of unmanned driving, and mainly aims to achieve turning of an unmanned vehicle on a narrow road with less time consumption, high accuracy and high comfort. The main technical scheme of the invention is as follows: determining a turning area based on surrounding scene information of the vehicle; calculating a first segmentation track based on the relative position of the vehicle in the turning area and the information of obstacles around the vehicle, wherein the ending position of the first segmentation track is the starting position of the vehicle for executing turning operation in the turning area; calculating a second segmentation track based on the termination position of the first segmentation track and the information of obstacles around the vehicle, wherein the termination position of the second segmentation track is the termination position of the vehicle completing the turning operation in the turning area; generating a u-turn trajectory of the vehicle based on the first and second segmented trajectories. The invention is used for turning around the unmanned vehicle in a narrow road.
Description
Technical Field
The invention relates to the technical field of unmanned driving, in particular to a vehicle turning track planning method and device.
Background
The unmanned vehicle is an intelligent vehicle integrating a plurality of technologies such as automatic control, visual calculation, architecture and the like, and a path planning system of the unmanned vehicle can generate a driving track according to surrounding scene information of the vehicle, so that the vehicle can accurately track and the driving safety of the vehicle is ensured. The narrow road turning is a typical and difficult scene of the unmanned vehicle in a complex scene of a city, the unmanned vehicle is on a long and narrow road, a reasonable decision-making idea needs to be designed in order to ensure that the vehicle can turn around, and the unmanned vehicle can turn around in the direction of the vehicle head under the condition of not driving away from the road surface after limited times of forward and backward.
Currently, in a narrow road turning scene, an unmanned vehicle usually judges forward, backward and steering angles directly according to preset conditions or according to a set calibrated threshold value, and then generates a turning trajectory planning route; and a U-turn trajectory planning route is generated by simultaneously generating a plurality of trajectories and then selecting and combining the trajectories.
However, the forward, backward and steering angles are directly judged according to preset conditions, and due to the fact that the scene is not systematically judged in advance, unnecessary forward or backward actions of the unmanned vehicle in the turning process are more, and not only is the algorithm time consuming, but also the comfort is low; the forward, backward and steering angles are directly judged according to the set calibrated threshold, although the calibrated threshold is universal and is suitable for most situations, the accuracy is poor aiming at the difference of different road conditions, and therefore the generated track accuracy is low; the method of generating the reselection combination by adopting multiple tracks simultaneously is not only complicated in steps, but also time-consuming. Therefore, the conventional generation method of the vehicle turning trajectory planning route has the problems of high time consumption, low accuracy and low comfort level.
Disclosure of Invention
In view of the above problems, the present invention provides a vehicle turning trajectory planning method and apparatus, and mainly aims to achieve turning of an unmanned vehicle on a narrow road with less time consumption, high accuracy and high comfort.
In order to solve the technical problems, the invention provides the following scheme:
in a first aspect, the present invention provides a vehicle turning trajectory planning method, including:
determining a turning area based on surrounding scene information of the vehicle;
calculating a first segmentation track based on the relative position of the vehicle in the turning area and the obstacle information around the vehicle, wherein the end position of the first segmentation track is the starting position of the vehicle for performing turning operation in the turning area;
calculating a second segmentation track based on the termination position of the first segmentation track and the information of obstacles around the vehicle, wherein the termination position of the second segmentation track is the termination position of the vehicle completing the turning operation in the turning area;
generating a u-turn trajectory of the vehicle based on the first and second segmented trajectories.
Preferably, the calculating of the second segmental track based on the end position of the first segmental track and the obstacle information around the vehicle includes:
calculating a second segmented track by using a hybrid A-star algorithm of a dynamic Cost function based on the end position of the first segmented track and the information of the obstacles around the vehicle; wherein the dynamic Cost function is: g (S, N) + H (x, y, theta), where S is the distance of the vehicle from a starting position to a target position in the G (S, N) function, and N is the number of times the vehicle switches forward or backward; and x and y in the H (x, y, theta) function are respectively the transverse position and the longitudinal position of the absolute coordinate system, and the theta is the heading angle of the vehicle.
Preferably, the calculating a first segment trajectory based on the relative position of the vehicle in the u-turn area and the obstacle information around the vehicle includes:
judging whether the tail part and the head part of the vehicle are positioned in the U-turn area at the same time;
if so, generating a mixed A star driving track by using a mixed A star algorithm;
if not, utilizing a Lattice algorithm to generate a fifth-order polynomial driving track.
Preferably, before the determining the u-turn region based on the surrounding scene information of the vehicle, the method further includes:
judging whether the width of a road where the vehicle is located is larger than the length of the vehicle body of the vehicle or not, and whether the sum of the distances between the vehicle and front and rear obstacles is larger than 3 lengths of the vehicle body or not;
if yes, determining that the vehicle can complete turning on the road, and determining a turning area based on surrounding scene information of the vehicle;
if not, determining that the vehicle cannot complete turning around on the road, generating a memory track according to the memory path data of the vehicle, and backing up the vehicle to return based on the memory track.
Preferably, before the generating the vehicle turning trajectory based on the first segment trajectory and the second segment trajectory, further includes:
segmenting according to the generating directions of the first segmented track and the second segmented track to obtain segmented tracks in different directions;
and determining a forward or backward gear corresponding to the vehicle running in the segmented track based on the generation direction of the segmented track.
Preferably, the determining the u-turn region includes:
acquiring peripheral obstacle information of the vehicle;
determining the boundary of an obstacle in the road where the vehicle is located based on the peripheral obstacle information of the vehicle;
and obtaining an interested area based on the length of the vehicle body of the vehicle and the boundary of the obstacle in the road where the vehicle is located, wherein the interested area is the turning area.
In a second aspect, the present invention provides a vehicle turning trajectory planning device, including:
a first determination unit configured to determine a u-turn region based on surrounding scene information of a vehicle;
a first calculating unit, configured to calculate a first segmentation track based on a relative position of the vehicle in the u-turn area and obstacle information around the vehicle, where a termination position of the first segmentation track is a start position of a u-turn operation performed by the vehicle in the u-turn area;
a second calculating unit, configured to calculate a second segmentation track based on an end position of the first segmentation track and obstacle information around the vehicle, where the end position of the second segmentation track is an end position of the vehicle at which a u-turn operation is completed in the u-turn area;
a first generating unit configured to generate a u-turn trajectory of the vehicle based on the first and second segment trajectories.
Preferably, the second calculating unit is further configured to calculate a second segmented trajectory by using a hybrid a-star algorithm of a dynamic Cost function based on the end position of the first segmented trajectory and the obstacle information around the vehicle; wherein the dynamic Cost function is: g (S, N) + H (x, y, theta), where S is the distance of the vehicle from a starting position to a target position in the G (S, N) function, and N is the number of times the vehicle switches forward or backward; and x and y in the H (x, y, theta) function are respectively the transverse position and the longitudinal position of the absolute coordinate system, and the theta is the heading angle of the vehicle.
Preferably, the first calculation unit includes:
the judging module is used for judging whether the tail part and the head part of the vehicle are positioned in the turning area at the same time;
the first generation module is used for generating a mixed A-star driving track by using a mixed A-star algorithm if the tail part and the head part of the vehicle are positioned in the U-turn area at the same time;
and the second generation module is used for generating a fifth-order polynomial driving track by utilizing a Lattice algorithm if the tail part and the head part of the vehicle are not positioned in the U-turn region at the same time.
Preferably, the apparatus further comprises:
the judging unit is used for judging whether the width of a road where the vehicle is located is larger than the length of the vehicle body of the vehicle or not and whether the sum of the distances between the vehicle and front and rear obstacles is larger than 3 lengths of the vehicle body or not;
the first determining unit is used for determining that the vehicle can complete turning on the road and determining a turning area based on the surrounding scene information of the vehicle if the width of the road where the vehicle is located is larger than the length of the vehicle body of the vehicle and the sum of the distances between the vehicle and the front and rear obstacles is larger than 3 lengths of the vehicle body;
and the second generation unit is used for determining that the vehicle cannot complete turning around on the road and generating a memory track according to the memory path data of the vehicle if the width of the road where the vehicle is located is not greater than the length of the vehicle body of the vehicle and the sum of the distances between the vehicle and the front obstacle and the rear obstacle is not greater than 3 lengths of the vehicle body, and the vehicle backs up and returns based on the memory track.
Preferably, the apparatus further comprises:
the acquisition unit is used for carrying out segmentation according to the generation directions of the first segmentation track and the second segmentation track to obtain segmentation tracks in different directions;
a second determination unit configured to determine a forward or reverse gear position corresponding to the vehicle traveling in the segmented trajectory based on the generation direction of the segmented trajectory.
Preferably, the first determination unit includes:
the acquisition module is used for acquiring the peripheral obstacle information of the vehicle;
the determining module is used for determining the boundary of an obstacle in a road where the vehicle is located based on the peripheral obstacle information of the vehicle;
the acquisition module is used for obtaining an interested area based on the length of the vehicle body of the vehicle and the boundary of an obstacle in the road where the vehicle is located, and the interested area is the turning area.
In order to achieve the above object, according to a third aspect of the present invention, there is provided a storage medium, the storage medium including a stored program, wherein when the program runs, the apparatus on which the storage medium is located is controlled to execute the vehicle u-turn trajectory planning method according to the first aspect.
In order to achieve the above object, according to a fourth aspect of the present invention, there is provided an electronic device, comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor executes the program to implement all or part of the steps of the vehicle turning trajectory planning apparatus for the vehicle turning trajectory planning apparatus according to the first aspect.
By means of the technical scheme, the vehicle turning track planning method and the vehicle turning track planning device provided by the invention have the advantages that the generated track is low in accuracy, time consumption and comfort level because the unmanned vehicle directly judges forward, backward and steering angles according to preset conditions or set calibrated thresholds in a narrow road turning scene, and a track mode of simultaneously generating and reselecting and combining multiple tracks is adopted. For this reason, the invention determines the turning area based on the surrounding scene information of the vehicle; calculating a first segmentation track based on the relative position of the vehicle in the turning area and the obstacle information around the vehicle, wherein the end position of the first segmentation track is the starting position of the vehicle for executing turning operation in the turning area; calculating a second segmentation track based on the termination position of the first segmentation track and the information of obstacles around the vehicle, wherein the termination position of the second segmentation track is the termination position of the vehicle completing the turning operation in the turning area; and finally generating the turning track of the vehicle based on the first segmented track and the second segmented track. The U-turn track generated by the invention is determined according to the real-time scene information of the road where the vehicle is located, does not depend on the preset condition and the calibration threshold, has higher accuracy and systematicness, reduces unnecessary execution operation to the maximum extent, and has high comfort degree and less time consumption.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 shows a flowchart of a vehicle turning trajectory planning method provided by an embodiment of the invention;
FIG. 2 is a flow chart of another vehicle turning trajectory planning method provided by the embodiment of the invention;
fig. 3 is a block diagram illustrating components of a vehicle u-turn trajectory planning apparatus according to an embodiment of the present invention;
fig. 4 is a block diagram illustrating another vehicle turning trajectory planning apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In the current narrow-road turning scene, the unmanned vehicle usually judges forward, backward and steering angles directly according to preset conditions or according to a set calibrated threshold value so as to generate a turning track planning route; and a U-turn trajectory planning route is generated by simultaneously generating a plurality of trajectories and then selecting and combining the trajectories. However, the existing turning track generation method can cause more unnecessary forward or backward actions of the unmanned vehicle in the turning process, and not only is the algorithm time consuming, but also the comfort is low; and the accuracy is also low. In view of this problem, the inventors conceived to solve the above problem by performing a two-stage trajectory generation manner according to scene information around a road where a vehicle is located.
Therefore, the embodiment of the invention provides a vehicle turning track planning method, by which an unmanned vehicle can complete turning in a narrow road with less time consumption, high accuracy and high comfort, and the specific implementation steps are as shown in fig. 1, and the method comprises the following steps:
101. the u-turn area is determined based on the surrounding scene information of the vehicle.
The surrounding scene information of the vehicle is derived from environment data collected by a high-precision map, a laser radar, a millimeter wave radar, an ultrasonic radar, a panoramic camera and the like, and the step is not particularly limited. The surrounding scene information of the vehicle includes the width, length, number of obstacles, size, and the like of the road on which the vehicle is located, and this step is not particularly limited.
And planning an area range in which the vehicle can turn around according to the scene information around the vehicle, wherein the area range does not comprise obstacles, and the area is a vehicle turning area.
102. And calculating a first segmentation track based on the relative position of the vehicle in the turning area and the information of obstacles around the vehicle, wherein the ending position of the first segmentation track is the starting position of the vehicle for executing the turning operation in the turning area.
Wherein the relative position of the vehicle in the turning area comprises that the vehicle is entirely in the turning area, the vehicle is partially in the turning area, and the vehicle is not entirely in the turning area. The obstacles around the vehicle include a road block, a fence, a utility pole, other vehicles, and the like, and this step is not particularly limited.
Calculating a first segmentation track based on the relative position of the vehicle in the turning area and the obstacle information around the vehicle, wherein the adopted calculation method can be a Lattice track or a mixed A, and the step is not limited specifically; the first segment trajectory is planned in order to drive a vehicle at any position in a road to a specified position of the u-turn area (i.e., an end position of the first segment trajectory), where the specified position is a start position for performing a u-turn operation, and the specified position may be set to any one of four corners of the u-turn area, and this step is not particularly limited. The vehicle moves to the designated position of the turning area based on the first subsection track to provide larger operable space than when the vehicle performs the turning operation at the original position of the road; and performing the turning operation based on the end point position of the first subsection track can realize higher turning success rate under the same road environment.
103. And calculating a second segmentation track based on the termination position of the first segmentation track and the information of obstacles around the vehicle, wherein the termination position of the second segmentation track is the termination position of the vehicle for completing the U-turn operation in the U-turn area.
According to the step 102, the ending position of the first segmented track is the starting position of the second segmented track, the second segmented track is calculated based on the ending position of the first segmented track and the information of obstacles around the vehicle, the adopted calculation method can be a Lattice track or a mixed A, and the step is not limited specifically; the planning purpose of the second segmented track is to perform turning around of the vehicle based on the ending position of the first segmented track as the starting position of the first segmented track; and the end position of the second segmentation track is the end position of the vehicle for completing the turning operation in the turning area.
104. And generating a turning track of the vehicle based on the first segmentation track and the second segmentation track.
Combining the first segmented track generated in the step 102 and the second segmented track generated in the step 103 to obtain a complete turning track of the vehicle; the vehicle can successfully turn around on the road according to the generated turning track, and does not collide with any obstacle.
Based on the implementation manner of the embodiment shown in fig. 1, it can be seen that the method for planning the turning-around trajectory of the vehicle provided by the invention has the problems of low accuracy, high time consumption and low comfort level of the generated trajectory due to the fact that the forward, backward and steering angles of the existing unmanned vehicle are directly judged according to the preset conditions or the set calibrated threshold value, and the trajectory manner of simultaneously generating and reselecting a combination by adopting multiple trajectories is adopted. The invention determines the turning area based on the surrounding scene information of the vehicle, can eliminate surrounding obstacles and define the required controllable space so as to facilitate the subsequent design of the turning track; calculating a first segmentation track based on the relative position of the vehicle in the turning area and the information of obstacles around the vehicle, wherein the termination position of the first segmentation track is the initial position of the vehicle for performing turning operation in the turning area, so that a larger operation space can be provided for turning of the vehicle, and the success rate of turning of the vehicle is improved in the same scene; calculating a second segmentation track based on the termination position of the first segmentation track and the information of obstacles around the vehicle, wherein the termination position of the second segmentation track is the termination position of the vehicle for completing the U-turn operation in the U-turn area; and finally generating the turning track of the vehicle based on the first segmented track and the second segmented track. The U-turn track generated by the invention is determined according to the real-time scene information of the road where the vehicle is located, does not depend on the preset condition and the calibration threshold, has higher accuracy and systematicness, reduces unnecessary execution operation to the maximum extent, and has high comfort degree and less time consumption.
Further, as a refinement and an extension of the embodiment shown in fig. 1, the embodiment of the present invention further provides another vehicle turning trajectory planning method, as shown in fig. 2, which specifically includes the following steps:
201. judging whether the width of a road where a vehicle is located is larger than the length of the vehicle body of the vehicle or not and whether the sum of the distances between the vehicle and front and rear obstacles is larger than 3 lengths of the vehicle body or not; if yes, determining that the vehicle can complete turning on the road, and determining a turning area based on the surrounding scene information of the vehicle; if not, determining that the vehicle cannot complete turning around on the road, generating a memory track according to memory path data of the vehicle, and backing up the vehicle to return based on the memory track.
The front and rear obstacles of the vehicle include other vehicles, telegraph poles, walls and the like, and the step is not limited specifically. The vehicle acquires the scene information of the vehicle around the road through technical means such as a high-precision map, a laser radar, a millimeter wave radar, an ultrasonic radar and a panoramic camera, and the step is not limited specifically. The collected surrounding scene information comprises the width of the road, the size information of obstacles around the vehicle and the distance information of the obstacles from the vehicle; and calculating the sum of the distance between the vehicle and the closest obstacle to the front end and the rear end of the vehicle based on the distance between the vehicle and the obstacle around the vehicle.
Judging whether the width of the road where the vehicle is located is larger than the length of the vehicle body of the vehicle or not, and whether the sum of the distances between the vehicle and front and rear obstacles is larger than 3 lengths of the vehicle body or not; if yes, determining that the vehicle can complete turning around on the road, and performing step 202 to determine a turning-around area based on surrounding scene information of the vehicle; if not, determining that the vehicle cannot complete turning around on the road, and generating a memory track according to memory path data of the vehicle, wherein the memory path data are sourced from a high-precision map, vehicle positioning track data, vehicle road and surrounding environment information; the method for generating the memory track needs to meet the constraint, smoothness, comfort and safety of vehicle kinematics, so that the OSQP optimization solution algorithm based on the memory data discrete points is preferred but not limited; the memorized track is used as a track of the vehicle leaving the road, and the vehicle backs up and returns based on the memorized track.
By the steps, scene information around a road where the vehicle is located can be comprehensively grasped in advance, and whether the vehicle can complete turning around or not can be judged in advance based on the acquired information, so that repeated detection processes according to preset conditions or calibrated thresholds can be reduced, unnecessary operation actions generated by repeated detection processes can be reduced, and the comfort level is improved; compared with preset conditions and a calibration threshold value, the step can accurately predict the road conditions in real time, and the accuracy is higher.
202. The u-turn area is determined based on the surrounding scene information of the vehicle.
The same contents of this step and step 101 are not described herein again.
As can be seen from step 101, the surrounding scene information of the vehicle is derived from the environmental data collected by the high-precision map, the laser radar, the millimeter wave radar, the ultrasonic radar, the panoramic camera, and the like, and the surrounding scene information of the vehicle includes the width, the length, the number of obstacles, the size, and the like of the road where the vehicle is located, which is not particularly limited in this step. Determining the boundary of an obstacle in the road where the vehicle is located based on the peripheral obstacle information of the vehicle; obtaining an ROI (region of interest) area (namely an interested area) based on the length of the vehicle body of the vehicle and the boundary of an obstacle in the road where the vehicle is located, wherein the ROI area is generally rectangular, and can be a combination of a plurality of quadrangles if the obstacle limits; the region of interest is the turning region, which is an operating region for the vehicle to perform turning.
203. And calculating a first segmentation track based on the relative position of the vehicle in the turning area and the obstacle information around the vehicle, wherein the end position of the first segmentation track is the starting position of the vehicle for executing the turning operation in the turning area.
The same contents of this step and step 102 are not described herein again.
Judging whether the tail part and the head part of the vehicle are positioned in the U-turn area at the same time; if so, generating a hybrid A star driving track by using a hybrid A star algorithm, wherein the navigation angle of the vehicle is parallel to the lane direction; if not, utilizing a Lattice algorithm to generate a fifth-order polynomial driving track, wherein the navigation angle of the vehicle is parallel to the lane direction. The following illustrates the steps of generating the first segmented trajectory:
example 1: an unmanned vehicle is positioned in the middle of the U-turn area, the end position of the first segmentation track is the position of the lower left corner of the U-turn area,
whether the head portion of the unmanned vehicle is located in the turning area is judged, if yes, whether the tail portion of the unmanned vehicle is located in the turning area is further judged, and if yes, all vehicle bodies of the unmanned vehicle are determined to be located in the turning area.
If all the bodies of the unmanned vehicle are located in the turning area, generating a hybrid A-star driving track as a first segmented track by using a hybrid A-star algorithm, wherein the navigation angle of the vehicle is parallel to the lane direction, and backing up to the lower left corner of the ROI area based on the first segmented track.
Example 2: an unmanned vehicle is positioned at the outer position of the U-turn area, the termination position of the first segmentation track is the lower right corner position of the U-turn area,
judging whether the head part of the unmanned vehicle is located in the turning area, if not, further judging whether the tail part of the unmanned vehicle is located in the turning area, and if not, determining that all vehicle bodies of the unmanned vehicle are located outside the turning area.
If all the bodies of the unmanned vehicle are located outside the turning area, generating a quintic polynomial driving track as a first segmented track by utilizing a Lattice algorithm, wherein the navigation angle of the vehicle is parallel to the lane direction, and the vehicle advances to the lower right corner of the ROI area based on the first segmented track.
204. And calculating a second segmentation track based on the termination position of the first segmentation track and the information of obstacles around the vehicle, wherein the termination position of the second segmentation track is the termination position of the vehicle for completing the turning operation in the turning area.
The same contents of this step and step 103 are not described herein again.
Calculating a second segmented track by using a hybrid A-star algorithm of a dynamic Cost function adapted to the narrow-path turning condition based on the end position of the first segmented track and the information of obstacles around the vehicle; wherein the dynamic Cost function is: g (S, N) + H (x, y, theta), where S is the distance of the vehicle from a starting position to a target position in the G (S, N) function, and N is the number of times the vehicle switches forward or backward; and in the H (x, y, theta) heuristic function, x and y are respectively the transverse position and the longitudinal position of an absolute coordinate system, and the theta is the heading angle of the vehicle.
After a second segmented track is generated for the first time, optimizing the second segmented track by detecting whether an obstacle exists in the second segmented track; if the second segmented track is detected to have no obstacles, determining the primarily generated second segmented track as a final second segmented track; and if the second segmented track is detected to have the obstacle, continuing searching until a track without the obstacle is searched, and generating a complete path as a final second segmented track after smoothing the track without the obstacle.
Wherein G (S, N) considers the Cost of shifting in addition to the distance S from the starting position to the target position to reduce the number N of forward and backward switching; the design of the H (x, y, theta) heuristic function comprises the heading angle theta of the vehicle besides the RS curve lengths of the transverse and longitudinal positions x and y of the absolute coordinate system; the weight of theta is larger than the track proportion of general parking, the steering wheel angle is limited in some parking tracks, and the steering wheel angle is not limited in the step; because the steering wheel angle required for turning the vehicle around is relatively large.
205. And generating a turning track of the vehicle based on the first segmentation track and the second segmentation track.
The same contents of this step and step 104 are not described herein again.
Before the generating the vehicle u-turn trajectory based on the first segment trajectory and the second segment trajectory, further comprising: segmenting according to the generating directions of the first segmented track and the second segmented track to obtain segmented tracks in different directions; and determining a forward or backward gear corresponding to the vehicle running in the segmented track based on the generation direction of the segmented track.
Based on the implementation manner of fig. 2, it can be seen that the invention provides a vehicle turning track planning method, by judging whether a vehicle can turn around on a road, the invention can reduce the repeated detection process according to the preset condition or the calibrated threshold, and also reduce the unnecessary operation actions generated thereby, and improve the comfort; compared with preset conditions and a calibration threshold value, the step is used for accurately prejudging according to real-time road conditions, and the accuracy is higher; by judging whether the vehicle is positioned inside or outside the U-turn area, respectively generating a driving track by using a hybrid A-star algorithm Lattice algorithm according to different relative positions of the vehicle in the U-turn area, and driving the vehicle to a specified position of the U-turn area, a larger U-turn operation space can be provided, and the U-turn success rate can be improved; calculating a second subsection track through a hybrid A-star algorithm of a dynamic Cost function, and obtaining a smooth, comfortable and safe U-turn track; and determining a forward or backward gear corresponding to the vehicle running in the segmented track based on the generation direction of the segmented track. Therefore, compared with the prior art, the U-turn track generated by the invention has high accuracy, reduces unnecessary execution operation to the maximum extent and has high comfort; and the process of generating the U-turn track is systematic, unnecessary operation is avoided, and the consumed time is short.
Further, as an implementation of the method shown in fig. 1, an embodiment of the present invention further provides a vehicle turning trajectory planning device, which is used for implementing the method shown in fig. 1. The embodiment of the apparatus corresponds to the embodiment of the method, and for convenience of reading, details in the embodiment of the apparatus are not repeated one by one, but it should be clear that the apparatus in the embodiment can correspondingly implement all the contents in the embodiment of the method. As shown in fig. 3, the apparatus includes:
a first determination unit 31 for determining a u-turn area based on surrounding scene information of the vehicle;
a first calculating unit 32 configured to calculate a first segment trajectory based on the relative position of the vehicle in the u-turn area obtained from the first determining unit 31 and obstacle information around the vehicle, the end position of the first segment trajectory being a start position where the vehicle performs a u-turn operation in the u-turn area;
a second calculating unit 33, configured to calculate a second segmentation trajectory based on the termination position of the first segmentation trajectory obtained from the first calculating unit 32 and the obstacle information around the vehicle, where the termination position of the second segmentation trajectory is a termination position where the vehicle completes a u-turn operation in the u-turn area;
a first generating unit 34 configured to generate a u-turn trajectory of the vehicle based on the first segmented trajectory obtained from the first calculating unit 32 and the second segmented trajectory obtained from the second calculating unit 33.
Further, as an implementation of the method shown in fig. 2, another vehicle turning trajectory planning device is further provided in an embodiment of the present invention, and is used for implementing the method shown in fig. 2. The embodiment of the apparatus corresponds to the embodiment of the method, and for convenience of reading, details in the embodiment of the apparatus are not repeated one by one, but it should be clear that the apparatus in the embodiment can correspondingly implement all the contents in the embodiment of the method. As shown in fig. 4, the apparatus includes:
the judging unit 35 is configured to judge whether the width of a road where the vehicle is located is greater than the length of a vehicle body of the vehicle, and whether the sum of distances from the vehicle to front and rear obstacles is greater than 3 lengths of the vehicle body;
the first determining unit 31 is configured to determine that the vehicle can complete a u-turn on the road and determine a u-turn area based on the surrounding scene information of the vehicle if the width of the road where the vehicle is located is greater than the length of the vehicle body of the vehicle and the sum of the distances between the vehicle and the front and rear obstacles is greater than 3 lengths of the vehicle body, which are obtained from the determining unit 35;
a second generating unit 36, configured to determine that the vehicle cannot turn around on the road if the width of the road where the vehicle is located is not greater than the length of the vehicle body of the vehicle and the sum of the distances between the vehicle and the front and rear obstacles is not greater than 3 lengths of the vehicle body, which are obtained from the determining unit 35, and generate a memory track according to the memory path data of the vehicle, where the vehicle backs up and returns based on the memory track.
A first calculating unit 32, configured to calculate a first segmentation trajectory based on the relative position of the vehicle in the u-turn area obtained from the first determining unit 31 and obstacle information around the vehicle, where an end position of the first segmentation trajectory is a start position of a u-turn operation performed by the vehicle in the u-turn area;
a second calculating unit 33, configured to calculate a second segmentation trajectory based on the termination position of the first segmentation trajectory obtained from the first calculating unit 32 and the obstacle information around the vehicle, where the termination position of the second segmentation trajectory is a termination position where the vehicle completes a u-turn operation in the u-turn area;
the second calculating unit 33 is further configured to calculate a second segmented trajectory by using a hybrid a-star algorithm of a dynamic Cost function based on the end position of the first segmented trajectory and the obstacle information around the vehicle; wherein the dynamic Cost function is: g (S, N) + H (x, y, theta), where S is the distance of the vehicle from a starting position to a target position in the G (S, N) function, and N is the number of times the vehicle switches forward or backward; and x and y in the H (x, y, theta) function are respectively the transverse position and the longitudinal position of the absolute coordinate system, and the theta is the heading angle of the vehicle.
An obtaining unit 37, configured to perform segmentation according to the first segmented trajectory obtained from the first calculating unit 32 and the second segmented trajectory obtained from the second calculating unit 33, so as to obtain segmented trajectories in different directions;
a second determining unit 38, configured to determine a forward or reverse gear position corresponding to the vehicle traveling in the segmented trajectory based on the generation direction of the segmented trajectory obtained from the obtaining unit 37.
A first generating unit 34 configured to generate a u-turn trajectory of the vehicle based on the first segmented trajectory obtained from the first calculating unit 32 and the second segmented trajectory obtained from the second calculating unit 33.
Further, the first calculation unit 32 includes:
a judging module 321, configured to judge whether the vehicle tail and the vehicle head of the vehicle are located in the u-turn region at the same time;
a first generating module 322, configured to generate a hybrid a-star driving trajectory by using a hybrid a-star algorithm if the vehicle tail portion and the vehicle head portion of the vehicle obtained from the determining module 321 are located in the u-turn region at the same time;
a second generating module 323, configured to generate a fifth-order polynomial driving trajectory by using a Lattice algorithm if the vehicle tail portion and the vehicle head portion of the vehicle obtained from the determining module 321 are not located in the u-turn region at the same time.
Further, the first determining unit 31 includes:
the acquisition module 311 is configured to acquire surrounding obstacle information of the vehicle;
a determining module 312, configured to determine a boundary of an obstacle in a road where the vehicle is located based on the peripheral obstacle information of the vehicle obtained from the acquiring module 311;
an obtaining module 313, configured to obtain an area of interest based on the length of the vehicle body of the vehicle and the boundary of the obstacle in the road where the vehicle is located, where the area of interest is the u-turn area.
Further, an embodiment of the present invention further provides a processor, where the processor is configured to execute a program, where the program executes the method for planning a u-turn trajectory of a vehicle described in fig. 1-2 when running.
Further, an embodiment of the present invention further provides a storage medium, where the storage medium is used to store a computer program, where the computer program, when running, controls a device in which the storage medium is located to execute the vehicle u-turn trajectory planning method described in fig. 1-2 above.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It will be appreciated that the relevant features of the method and apparatus described above are referred to one another. In addition, "first", "second", and the like in the above embodiments are used to distinguish the embodiments, and do not represent merits of the embodiments.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In addition, the memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A vehicle turning trajectory planning method is characterized by comprising the following steps:
determining a turning area based on surrounding scene information of the vehicle;
calculating a first segmentation track based on the relative position of the vehicle in the turning area and the information of obstacles around the vehicle, wherein the ending position of the first segmentation track is the starting position of the vehicle for executing turning operation in the turning area;
calculating a second segmentation track based on the termination position of the first segmentation track and the information of obstacles around the vehicle, wherein the termination position of the second segmentation track is the termination position of the vehicle completing the turning operation in the turning area;
generating a u-turn trajectory of the vehicle based on the first segmented trajectory and the second segmented trajectory.
2. The method of claim 1, wherein the calculating a second segmented trajectory based on the ending location of the first segmented trajectory and the obstacle information around the vehicle comprises:
calculating a second segmented track by using a hybrid A-star algorithm of a dynamic Cost function based on the end position of the first segmented track and the information of the obstacles around the vehicle; wherein the dynamic Cost function is: g (S, N) + H (x, y, theta), where S is the distance of the vehicle from a starting position to a target position in the G (S, N) function, and N is the number of times the vehicle switches forward or backward; and x and y in the H (x, y, theta) function are respectively the transverse position and the longitudinal position of the absolute coordinate system, and the theta is the heading angle of the vehicle.
3. The method of claim 1, wherein the calculating a first segmented trajectory based on the relative position of the vehicle in the u-turn area and obstacle information around the vehicle comprises:
judging whether the tail part and the head part of the vehicle are positioned in the U-turn area at the same time;
if so, generating a mixed A star driving track by using a mixed A star algorithm;
if not, utilizing a Lattice algorithm to generate a fifth-order polynomial driving track.
4. The method according to claim 1, further comprising, before the determining a u-turn area based on the surrounding scene information of the vehicle:
judging whether the width of a road where the vehicle is located is larger than the length of the vehicle body of the vehicle or not, and whether the sum of the distances between the vehicle and front and rear obstacles is larger than 3 lengths of the vehicle body or not;
if yes, determining that the vehicle can complete turning on the road, and determining a turning area based on surrounding scene information of the vehicle;
if not, determining that the vehicle cannot complete turning around on the road, generating a memory track according to the memory path data of the vehicle, and backing up the vehicle to return based on the memory track.
5. The method of claim 1, further comprising, prior to the generating the vehicle u-turn trajectory based on the first segmented trajectory and the second segmented trajectory:
segmenting according to the generating directions of the first segmented track and the second segmented track to obtain segmented tracks in different directions;
and determining a forward or backward gear corresponding to the vehicle running in the segmented track based on the generation direction of the segmented track.
6. The method according to any one of claims 1 to 5, wherein the determining the u-turn area comprises:
acquiring peripheral obstacle information of the vehicle;
determining the boundary of an obstacle in the road where the vehicle is located based on the peripheral obstacle information of the vehicle;
and obtaining an interested area based on the length of the vehicle body of the vehicle and the boundary of the obstacle in the road where the vehicle is located, wherein the interested area is the turning area.
7. A vehicle turning trajectory planning apparatus, characterized in that the apparatus comprises:
a first determination unit configured to determine a u-turn region based on surrounding scene information of a vehicle;
a first calculating unit, configured to calculate a first segmentation track based on a relative position of the vehicle in the u-turn area and obstacle information around the vehicle, where a termination position of the first segmentation track is a start position of a u-turn operation performed by the vehicle in the u-turn area;
a second calculating unit, configured to calculate a second segmentation track based on an end position of the first segmentation track and obstacle information around the vehicle, where the end position of the second segmentation track is an end position of the vehicle at which a u-turn operation is completed in the u-turn area;
a first generating unit configured to generate a u-turn trajectory of the vehicle based on the first and second segment trajectories.
8. The apparatus according to claim 7, wherein the second calculation unit is further configured to calculate a second segmented trajectory using a hybrid a-star algorithm of a dynamic Cost function based on the end position of the first segmented trajectory and the obstacle information around the vehicle; wherein the dynamic Cost function is: f ═ G (S, N) + H (x, y, theta), where S is the distance of the vehicle from a starting position to a target position in the G (S, N) function, and N is the number of switches of forward or reverse of the vehicle; and x and y in the H (x, y, theta) function are respectively the transverse position and the longitudinal position of the absolute coordinate system, and the theta is the heading angle of the vehicle.
9. A storage medium comprising a stored program, wherein the program, when executed, controls an apparatus on which the storage medium is located to execute the vehicle turning trajectory planning method according to any one of claims 1 to 6.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the vehicle turning trajectory planning method according to any one of claims 1 to 6 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210694631.2A CN115097826A (en) | 2022-06-20 | 2022-06-20 | Vehicle turning track planning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210694631.2A CN115097826A (en) | 2022-06-20 | 2022-06-20 | Vehicle turning track planning method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115097826A true CN115097826A (en) | 2022-09-23 |
Family
ID=83290448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210694631.2A Pending CN115097826A (en) | 2022-06-20 | 2022-06-20 | Vehicle turning track planning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115097826A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116907532A (en) * | 2023-09-12 | 2023-10-20 | 城市之光(深圳)无人驾驶有限公司 | Method, device and equipment for planning narrow-road three-section turning path of unmanned vehicle |
-
2022
- 2022-06-20 CN CN202210694631.2A patent/CN115097826A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116907532A (en) * | 2023-09-12 | 2023-10-20 | 城市之光(深圳)无人驾驶有限公司 | Method, device and equipment for planning narrow-road three-section turning path of unmanned vehicle |
| CN116907532B (en) * | 2023-09-12 | 2023-11-21 | 城市之光(深圳)无人驾驶有限公司 | Method, device and equipment for planning narrow-road three-section turning path of unmanned vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200269873A1 (en) | Method and apparatus for planning speed of autonomous vehicle, and storage medium | |
| US20200265710A1 (en) | Travelling track prediction method and device for vehicle | |
| US10678248B2 (en) | Fast trajectory planning via maneuver pattern selection | |
| CN111750886B (en) | Local path planning method and device | |
| US20220080961A1 (en) | Control system and control method for sampling based planning of possible trajectories for motor vehicles | |
| CN111830979A (en) | Trajectory optimization method and device | |
| CN111338361A (en) | Obstacle avoidance method, device, equipment and medium for low-speed unmanned vehicle | |
| US20230099853A1 (en) | Methods and systems for vehicle path planning | |
| CN111522350A (en) | Sensing method, intelligent control equipment and automatic driving vehicle | |
| WO2021034819A1 (en) | Polyline contour representations for autonomous vehicles | |
| CN111923902A (en) | Parking control method and device, electronic equipment and storage medium | |
| CN113670305A (en) | Parking trajectory generation method and device, computer equipment and storage medium | |
| CN113561992B (en) | Automatic driving vehicle track generation method, device, terminal equipment and medium | |
| JP2022502311A (en) | Feature point extraction method and equipment for environmental targets | |
| CN114690765A (en) | Mine card self-adaptive retaining wall unloading parking method, device, system and computer equipment | |
| CN115077553A (en) | Method, system, automobile, equipment and medium for planning track based on grid search | |
| CN115097826A (en) | Vehicle turning track planning method and device | |
| WO2022216641A1 (en) | Counter-steering penalization during vehicle turns | |
| US10732632B2 (en) | Method for generating a reference line by stitching multiple reference lines together using multiple threads | |
| CN114435405A (en) | Vehicle lane changing method, device, equipment and storage medium | |
| CN116476840B (en) | Variable-lane driving method, device, equipment and storage medium | |
| CN114185337A (en) | Vehicle, and vehicle pre-collision detection method and device | |
| CN115683140A (en) | Method, system, equipment and medium for planning curve passing speed of passenger-riding parking tracking | |
| CN115014380A (en) | Parking path planning method and device, electronic device and storage medium | |
| CN114506314A (en) | Vehicle parallel parking method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 314500 988 Tong Tong Road, Wu Tong Street, Tongxiang, Jiaxing, Zhejiang Applicant after: United New Energy Automobile Co.,Ltd. Address before: 314500 988 Tong Tong Road, Wu Tong Street, Tongxiang, Jiaxing, Zhejiang Applicant before: Hezhong New Energy Vehicle Co.,Ltd. |
|
| CB02 | Change of applicant information |